{"mean_reward": 530.5, "std_reward": 156.1001281229455, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-03T10:26:44.366519"} |
{"mean_reward": 530.5, "std_reward": 156.1001281229455, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-03T10:26:44.366519"} |